Information processing device

Abstract

To achieve an information processing device having good usability for a user.SOLUTION: An information processing device disclosed in the present specification includes: an input unit to which information is input; an extraction unit for extracting prescribed words from the information input to the input unit; a classification unit which classifies the words extracted by the words into first words and second words; a conversion unit which converts the first words by a first conversion method, and converts the second words by a second conversion method being different from the first conversion method; and a determination unit which determines, according to a time point or a position of the user, whether to display the words converted by the first conversion method.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device. [Background technology]

[0002] Conventionally, mobile information terminals that assist users have been proposed. For example, Patent Document 1 proposes a technology for managing the schedule of a user by having the user record a voice message in a first server via a mobile phone, dividing the recorded message into multiple parts, and having multiple external secretaries convert each divided message into text, which is then stored in a second server.

[0003] Furthermore, Patent Document 2 proposes a technology in which a portable information terminal is provided with a voice input means and a communication means, voice input from the voice input means is transmitted to a voice recognition server via the communication means, and text information generated from the voice by the voice recognition server is received by the portable information terminal. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2006-309356 A [Patent Document 2] Japanese Patent Application Publication No. 7-222248 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional portable information terminals have not always been user-friendly, due to their lack of consideration for security and their complicated operation.

[0006] Therefore, the present invention has been made in consideration of the above problems, and an object of the present invention is to provide an information processing device that is easy to use. [Means for solving the problem]

[0007] The information processing device of the present invention comprises an input unit for inputting information, an extraction unit for extracting predetermined words from the information inputted to the input unit, a classification unit for classifying the words extracted by the extraction unit into first words and second words, a conversion unit for converting the first words using a first conversion method and converting the second words using a second conversion method different from the first conversion method, and a judgment unit for determining whether to display the words converted using the first conversion method depending on the time or the user's location. Effect of the Invention

[0008] The present invention has an effect of providing an information processing device that is easy to use. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a functional block diagram of a personal assistant system 100 according to an embodiment. [Diagram 2] 2(a) to 2(d) are flowcharts showing the process of recording the voice input from the voice input unit. [Diagram 3] FIG. 13 is a diagram showing a voiceprint DB. [Figure 4] 4 is a flowchart relating to processing of audio data. [Diagram 5] FIG. 13 is a diagram showing a stored data DB. [Figure 6] 5 is a flowchart showing a specific process of step S76 in FIG. 4. [Figure 7] FIG. 13 is a diagram showing a keyword DB. [Figure 8] 5 is a flowchart showing a specific process of step S84 in FIG. 4. [Figure 9] 9 is a flowchart showing a specific process of step S122 in FIG. 8. [Figure 10] 10 is a flowchart showing specific processes of steps S142 and S148 in FIG. 9. [Figure 11] FIG. 13 is a diagram showing a specific conversion word DB. [Figure 12] 11 is a flowchart showing specific processes of steps S164, S166, S178, and S180 in FIG. [Figure 13] FIG. 13 is a diagram showing a place name DB. [Figure 14] FIG. 13 is a diagram showing a keyword storage DB. [Figure 15] 15(a) to 15(d) are diagrams showing examples of weighting tables. [Figure 16] FIG. 13 is a diagram showing a keyword record DB. [Figure 17] FIG. 13 is a diagram showing a command DB. [Figure 18] FIG. 18(a) is a diagram showing an example of a displayed task list, and FIG. 18(b) is a diagram showing an example of a displayed recorded voice list. [Figure 19] 13 is a flowchart showing a first process performed simultaneously in parallel in step S96. [Figure 20] 13 is a flowchart showing a second process performed simultaneously in parallel in step S96. [Figure 21] 13 is a flowchart showing a third process performed simultaneously in parallel in step S96. [Figure 22] FIG. 13 is a diagram showing a secure range DB. [Figure 23] FIG. 13 is a diagram showing a fuzzy word DB. [Figure 24] 13 is a flowchart showing a data erasing process on the portable terminal side. [Diagram 25] 13 is a flowchart showing a process of deleting audio data on the server side; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An embodiment of the personal assistant system 100 will be described in detail below with reference to Fig. 1 to Fig. 25. Fig. 1 shows a block diagram of the personal assistant system 100. As shown in Fig. 1, the personal assistant system 100 includes a portable terminal 10 and a server 50.

[0011] The portable terminal 10 is a terminal that can be carried by a user, such as a mobile phone, a smartphone, a PHS (Personal Handy-phone System), or a PDA (Personal Digital Assistant). The size of the portable terminal 10 is such that it can be placed in a breast pocket, for example. As shown in FIG. 1, the portable terminal 10 has an input unit 12, a display unit 14, a playback unit 16, a warning unit 18, a biometric information input unit 20, a position detection unit 22, a time detection unit 24, a calendar unit 26, a flash memory 28, a communication unit 32, and a terminal-side control unit 30. The portable terminal 10 also has a portable portable terminal housing that stores at least a part of each of these units.

[0012] The input unit 12 has a voice input unit 42 and a text data input unit 44. The voice input unit 42 includes a microphone and acquires the user's voice and voices emitted around the user. The text data input unit 44 includes an input interface such as a keyboard or a touch panel and acquires text data according to the user's input operation. The input unit 12 also has a function of accepting user operation instructions from the touch panel or the like.

[0013] The display unit 14 includes a display such as a liquid crystal display, an organic EL display, etc. The display unit 14 displays data such as image data and character data on the display, and displays menus for the user to operate.

[0014] The playback unit 16 includes a speaker and outputs voice and sound. The warning unit 18 warns the user when an error occurs in the mobile terminal 10, for example, by outputting a warning sound via the playback unit 16 or displaying a warning on the display unit 14.

[0015] The bioinformation input unit 20 is a device that acquires at least one of the bioinformation such as the state of the user's muscles (degree of tension and relaxation), blood pressure, heart rate, pulse, and body temperature, and inputs it to the terminal-side control unit 30. As a method for detecting the bioinformation, for example, a wristwatch type as described in JP-A-2005-270543 can be adopted. Blood pressure and pulse can be detected by a pulse wave detection sensor using infrared rays, and the heart rate can be detected by a vibration sensor. When the heart rate is higher than normal, the user is in a state of tension, and when the heart rate is lower, the user is in a state of relaxation. In addition, since the pupils expand in a state of tension and contract in a state of relaxation, a configuration may be applied in which the pupils are detected to determine whether the user is in a state of tension or relaxation.

[0016] The position detection unit 22 detects the position (absolute position) of the user, and here, for example, a Global Positioning System (GPS) is adopted. Note that, as the position detection unit 22, an absolute position measurement system using RFID (Radio Frequency IDentification) or the like may be adopted.

[0017] The time detection unit 24 has a clocking function for detecting the current time. The calendar unit 26 stores dates and days of the week in association with each other. The flash memory 28 is a memory for temporarily storing data. The communication unit 32 has a wireless LAN unit for accessing an access point by WiFi communication, a wired connection unit by an Ethernet (registered trademark) cable, or a USB connection unit for communicating with an external device such as a computer. In this embodiment, the communication unit 32 can communicate with the communication unit 52 of the server 50.

[0018] The terminal control unit 30 comprehensively controls each component of the portable terminal 10 and executes processing on the side of the portable terminal 10. For example, the terminal control unit 30 acquires the time when the voice data is input to the voice input unit 42 via the time detection unit 24, and acquires the position of the portable terminal 10 when the voice data is input via the position detection unit 22. When transmitting the voice data to the server 50, the terminal control unit 30 also transmits information on the time and position together with the voice data.

[0019] The server 50 is installed, for example, in a company where a user who uses the portable terminal 10 works. However, the present invention is not limited to this, and the server 50 may be installed in a system management company. As shown in FIG. 1, the server 50 has a communication unit 52, a text data generation unit 54, a voiceprint analysis unit 55, a weighting unit 56, an extraction unit 58, a classification unit 60, a conversion unit 62, a flash memory 64, a hard disk 66, and a server-side control unit 70.

[0020] The communication unit 52 is similar to the communication unit 32 on the mobile terminal 10 side, and in this embodiment, is capable of communicating with the communication unit 32 on the mobile terminal 10 side. Data (audio data and text data) received by the communication unit 52 is stored in the flash memory 64 via the server-side control unit 70. That is, the communication unit 52 functions as a voice input unit and a text data input unit in the server 50.

[0021] The text data generating unit 54 acquires the voice data stored in the flash memory 64 and converts the voice data to generate text data. The generated text data is stored in the flash memory 64 via the server-side control unit 70.

[0022] The voiceprint analysis unit 55 performs voiceprint analysis by pattern matching with registered voiceprint data using the volume (strength), frequency, and length of the voice, and identifies the person who made the sound. Note that in the voiceprint analysis, it is not necessary to use all of the volume (strength), frequency, and length of the voice, and it is also possible to identify the person who made the sound by using at least the frequency of the voice.

[0023] The weighting unit 56 acquires the voice data stored in the flash memory 64 and the text data generated from the voice data, or the text data input from the text data input unit 44, and weights each piece of text data. The weighting unit 56 stores the numerical value (task priority) obtained by the weighting in the flash memory 64 together with the text data.

[0024] The weighting by the weighting unit 56 is performed based on, for example, the volume and frequency of the voice, and the meaning of the text data. Specifically, the weighting unit 56 performs weighting based on the result of analysis by the voiceprint analysis unit 55 based on the volume and frequency of the voice (information on who is the person who uttered the voice), or performs weighting according to confidentiality based on the meaning of the text data. In this embodiment, confidentiality means the degree to which it is preferable that the data not be seen by others (unspecified third parties).

[0025] The weighting unit 56 is connected to a change unit 72 and a setting unit 74. The change unit 72 changes the settings related to the weighting of the weighting unit 56, and the setting unit 74 changes the settings related to the weighting of the weighting unit 56 based on a user's instruction. The setting unit 74 may change the settings based on a user's instruction input from an input unit (keyboard, etc.) of the server, or may change the settings in response to a user's instruction input from the input unit 12 of the mobile terminal 10 via the communication units 52 and 32.

[0026] The extraction unit 58 extracts predetermined words from the text data stored in the flash memory 64. That is, the extraction unit 58 extracts predetermined words from the information input to the input unit 12 of the mobile terminal 10. The predetermined words refer to words that should not be seen by others, that is, words with relatively high confidentiality, and the words are predetermined in a keyword DB (see FIG. 7) stored in the hard disk 66.

[0027] The classification unit 60 classifies the words extracted by the extraction unit 58 into words with a high confidentiality level (first words) and words with a slightly high (medium) confidentiality level (second words). This classification is performed based on a keyword DB (see FIG. 7) stored in the hard disk 66. The conversion unit 62 converts words with a "high" confidentiality level and words with a "medium" confidentiality level based on a predetermined rule, and stores the converted words in the flash memory 64.

[0028] The flash memory 64 temporarily stores data to be processed within the server 50. An erasure unit 76 is connected to the flash memory 64. The erasure unit 76 erases the voice data and text data stored in the flash memory 64 at a predetermined timing based on an instruction from the server-side control unit 70. The specific timing for erasing the data will be described later. Instead of the flash memory 64, other volatile memories may be used.

[0029] Data such as databases used in various processes is stored in the hard disk 66. Instead of the hard disk 66, other non-volatile memory may be used.

[0030] The server-side control unit 70 comprehensively controls each unit in the server 50 and executes processes on the server 50 side. Note that the server 50 actually has a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and the CPU executes programs stored (installed) in the ROM, etc., to realize the functions of each unit, such as the text data generation unit 54, weighting unit 56, extraction unit 58, classification unit 60, conversion unit 62, and voiceprint analysis unit 55 described above.

[0031] Next, the processing in the personal assistant system 100 of this embodiment will be described in detail with reference to FIGS.

[0032] First, the process (recording process) of storing the voice input from the voice input unit 42 in the flash memory 64 on the server 50 side will be described with reference to Figures 2(a) to 2(d). Of course, the recording process may be performed at all times, but in this embodiment, in order to conserve power and perform efficient recording, at least two of the processes in Figures 2(a) to 2(d) are performed simultaneously in parallel, or only one of the processes is performed.

[0033] (Recording timing example 1) 2(a) is a flowchart showing a process for recording only while a person is making a sound. The sound input to the sound input unit 42 is assumed to be input to the server-side control unit 70 via the communication units 32 and 52.

[0034] In the process of FIG. 2(a), in step S10, the server-side control unit 70 judges whether or not a voice has been input from the voice input unit 42. If the judgment here is positive, in step S12, under the instruction of the server-side control unit 70, the voiceprint analysis unit 55 performs a voiceprint analysis of the input voice. In this voiceprint analysis, the person who uttered the input voice is identified by comparing (pattern matching) the voice data included in the voiceprint DB (see FIG. 3) stored in the hard disk 66 with the input voice data. Here, in the voiceprint DB of FIG. 3, the person's name is associated with the voiceprint data of the person. When this system is used for business purposes, for example, the voiceprint data of all the employees of the company can be registered in the voiceprint DB. When this system is used for private purposes, each user can individually register the voiceprint data of family members, relatives, friends, etc. in the voiceprint DB. This registration is performed from the voice input unit 42 of the mobile terminal 10.

[0035] Next, in step S14, the server-side control unit 70 determines whether or not a person was identified in step S12, i.e., whether or not the voice is that of a person registered in the voiceprint DB. If the determination here is positive, the server-side control unit 70 starts recording (storing in the flash memory 64) in step S16. Note that since the recorded voice data is converted into text data in the text data generating unit 54, the timing at which recording starts can also be said to be the timing at which the text data is generated. On the other hand, if the determination in step S14 is negative, the process returns to step S10.

[0036] After the determination in step S14 is affirmative and the process proceeds to step S16, the server-side control unit 70 continues recording until the voice input ceases for a predetermined second in step S18. If there is no voice input for the predetermined second, that is, if the voice input is deemed to have ended, the determination in step S18 is affirmative. If the determination in step S18 is affirmative, the terminal-side control unit 30 ends recording in step S20 and returns to step S10.

[0037] After that, by repeating the above process, recording is performed every time a person registered in the voiceprint DB speaks. The person who decides the recording timing may be managed in a DB separate from the voiceprint DB. This makes it possible to limit the person who decides the recording timing to, for example, the organizer of the meeting.

[0038] 2(a) shows a case where recording is started when a person speaks based on the voiceprint, but the present invention is not limited to this. For example, recording may be started when a frequency related to a telephone call (e.g., a frequency of a ringtone) is input from the voice input unit 42. This makes it possible to record a telephone conversation without missing anything.

[0039] (Recording timing example 2) Fig. 2(b) is a flow chart showing the process of executing recording at a pre-registered time. Note that the process of Fig. 2(b) differs from that of Fig. 2(a) in that the recording timing is switched by switching whether or not to transmit voice data from the communication unit 32 of the mobile terminal 10 to the server 50.

[0040] In FIG. 2(b), in step S24, the terminal control unit 30 detects the current time via the time detection unit 24. Next, in step S26, the terminal control unit 30 judges whether it is a predetermined recording start time. Here, the recording start time may be predetermined when the mobile terminal 10 is shipped, or may be input in advance by a user or the like via the input unit 12. This recording start time may be, for example, a time when there is a lot of conversation with people and the like and when the amount of information is considered to be large (for example, one hour immediately after arriving at work), or a time when concentration is likely to be broken (for example, 30 minutes before or after a lunch break, or overtime hours (after 8 p.m., etc.) when fatigue reaches its peak).

[0041] If the determination in step S26 is positive, the process proceeds to step S28, where the communication unit 32 starts transmitting the voice data input to the voice input unit 42 to the server 50 under the instruction of the terminal-side control unit 30. In this case, the voice data is stored (recorded) in the flash memory 64 via the communication unit 52 and the server-side control unit 70.

[0042] Next, in step S30, the terminal control unit 30 detects the current time via the time detection unit 24. Then, in the next step S32, the terminal control unit 30 judges whether or not a predetermined recording end time has arrived. If the judgment here is positive, the process proceeds to step S34, but if the judgment here is negative, the process returns to step S30. If the process proceeds to step S34, the communication unit 32 stops transmitting audio data to the server 50 under the instruction of the terminal control unit 30. This ends the recording. After that, the process returns to step S24, and the above process is repeated. This allows recording to be performed every time the recording start time arrives.

[0043] (Recording timing example 3) Fig. 2(c) is a flow chart showing the process of recording at the end of a pre-registered conference. Note that, like Fig. 2(b), the process of Fig. 2(c) also switches the recording timing by switching whether or not to transmit audio data from the communication unit 32 to the server 50.

[0044] In Fig. 2(c), in step S36, the terminal-side control unit 30 detects the current time via the time detection unit 24. Next, in step S38, the terminal-side control unit 30 extracts a meeting schedule from a task list (described later) stored in the flash memory 28, and judges whether it is a predetermined time (e.g., 10 minutes) before the end of the meeting. If the judgment here is positive, in step S40, recording is started in the same manner as in step S28 in Fig. 2(b).

[0045] In the next step S42, the terminal control unit 30 detects the current time via the time detection unit 24. Then, in the next step S44, the terminal control unit 30 judges whether the end time of the conference used in the judgment of step S38 has arrived. If the judgment here is positive, the process proceeds to step S46, but if the judgment is negative, the process returns to step S42. If the process proceeds to step S46, the communication unit 32 stops transmitting voice data to the server 50 under the instruction of the terminal control unit 30. Thereafter, the process returns to step S36 and the above process is repeated. This makes it possible to record the audio at a predetermined time toward the end of the conference. The reason why the audio is recorded toward the end of the conference is that the closer the conference is to the end, the more likely it is that the conclusion of the conference will be announced or the schedule for the next conference will be announced.

[0046] In addition, the process in Fig. 2(c) may be set to record continuously for the duration of the conference. Also, if the chairperson or presenters of the conference are registered in the task list, it may be combined with the process in Fig. 2(a) to record only the voices of the registered chairperson or presenters.

[0047] (Recording timing example 4) Fig. 2(d) is a flow chart showing a process of executing recording based on information (here, the state of the user's muscles (degree of tension and degree of relaxation)) input from the bioinformation input unit 20. Note that, like Fig. 2(b) and Fig. 2(c), the process of Fig. 2(d) also switches the timing of recording by switching whether or not to transmit voice data from the communication unit 32 to the server 50 side.

[0048] In Fig. 2(d), in step S50, the terminal-side controller 30 acquires the state of the user's muscles via the biometric information input unit 20. Next, in step S52, the terminal-side controller 30 compares the state of the muscles with a predetermined threshold value to determine whether or not the muscles are in a predetermined relaxed state. If the determination here is positive, in step S54, recording is started in the same manner as in step S28 in Fig. 2(b).

[0049] In the next step S56, the terminal-side control unit 30 acquires the muscle state again. In the next step S58, the terminal-side control unit 30 compares the muscle state with a predetermined threshold value to determine whether or not the muscle state is in a predetermined tense state. If the determination here is positive, the process proceeds to step S60, but if the determination here is negative, the process returns to step S56. If the process proceeds to step S60, the communication unit 32 stops transmitting voice data to the server 50 under the instruction of the terminal-side control unit 30. Thereafter, the process returns to step S50 and the above process is repeated. Through the above process, it becomes possible to determine the user's level of tension from the muscle state and automatically record voice in a situation where the user is too relaxed and not listening to others (for example, a situation where the user is dozing off).

[0050] In Fig. 2(d), the voice is recorded only when the person is too relaxed, but in addition to or instead of this, the voice may be recorded when the person is moderately tense. This is because when the person is moderately tense, there is a high possibility that important talk is taking place.

[0051] In addition, at least one of a sweat sensor and a pressure sensor may be provided in the handset (portable terminal housing) to detect whether the user is in a tense or relaxed state based on the amount of sweat in the hand holding the handset or the strength with which the handset is held.

[0052] The outputs of the sweat sensor and pressure sensor may be transmitted to the terminal control unit 30, and the terminal control unit 30 may start recording by the voice input unit 42 when it determines that the user is in a tense or relaxed state.

[0053] The perspiration sensor can be provided with multiple electrodes to measure the impedance of the hand. Since emotional sweating due to emotion, excitement, or nervousness produces a small amount of sweat and the duration of sweating is short, the receiver can be provided with a perspiration sensor corresponding to the palm side of the middle hand, which produces more sweat than the fingers.

[0054] The pressure sensor may be of the capacitance type, a strain gauge, or an electrostrictive element, and it may be determined that the user is in a tense state when he or she grips the receiver with a pressure that is, for example, 10% or more greater than the pressure with which the user would normally grip the receiver.

[0055] Furthermore, at least one of the perspiration sensor and the pressure sensor may be provided in the portable terminal 10, or in a mobile phone or the like.

[0056] As described above, even when the timing to start recording has come in the processing of Figures 2(a) to 2(d), recording may not start if, for example, the mobile terminal 10 is in a recording prohibited location. An example of a recording prohibited location may be within a company other than the company where the user works.

[0057] (Audio data processing) Next, the processing of the audio data that is performed after the audio data is recorded will be described with reference to Fig. 4 to Fig. 23. Fig. 4 is a flowchart relating to the processing of the audio data.

[0058] In step S70 of FIG. 4, the server-side control unit 70 judges whether or not voice data has been recorded in the flash memory 64. If the judgment here is positive, the process proceeds to step S72, where the text data generating unit 54 converts the voice data into text under the instruction of the server-side control unit 70. In this case, the voice data is converted into text every time the voice data is interrupted for a predetermined period of time. The server-side control unit 70 also registers the data (text data) obtained by converting the voice data into text, the time when the voice data was input to the voice input unit 42, the position where the voice data was input, and the voice level of the voice data in the stored data DB (FIG. 5) in the flash memory 64. Note that the information on the time and position registered here is transmitted from the communication unit 32 together with the voice data, as described above. Next, in step S74, the voiceprint analysis unit 55, under the instruction of the server-side control unit 70, performs a voiceprint analysis to identify the person who made the voice, and registers the person in the stored data DB. It should be noted that if the process of step S12 in FIG. 2(a) has been performed, the content of step S12 may be registered in the stored data DB without performing step S74.

[0059] The data structure of the stored data DB is shown in Fig. 5. The stored data DB stores the above-mentioned time, position, text data, speaker, voice level, task flag, and task priority. The items of task flag and task priority will be described later.

[0060] Returning to FIG. 4, in the next step S76, a task determination subroutine is executed. In the task determination subroutine, the process of FIG. 6 is executed as an example. In the process of FIG. 6, in step S110, the server-side control unit 70 judges whether or not the text data includes a date and time. The date and time here includes not only a specific date and time such as a year, month, day, and time, but also dates and times such as tomorrow, the day after tomorrow, morning, and afternoon. If the judgment here is positive, the process proceeds to step S78 in FIG. 4 after it is judged to be a task in step S114, but if the judgment here is negative, the process proceeds to step S112.

[0061] In step S112, the server-side control unit 70 judges whether or not the text data contains a specific word. Here, the specific word is a word related to a task, such as "to do," "please," "do," "do," "do," "try," "will," "will," "plan," and the like. The specific word may be stored in the hard disk 66 as a table beforehand at the time of shipment of the device, or may be added by the user at any time. If the judgment in step S112 is positive, the data is judged to be a task in step S114, and the process proceeds to step S78 in FIG. 4. On the other hand, if the judgment in step S112 is negative, the data is judged to be not a task in step S116, and the process proceeds to step S78 in FIG. 4.

[0062] Returning to Fig. 4, in step S78, the server-side control unit 70 judges whether or not the task has been determined as a result of the processing in Fig. 6. Below, the processing when the judgment in step S78 is positive and when it is negative will be described.

[0063] (If the determination in step S78 is affirmative (if it is a task)) If the determination in step S78 is positive, the process proceeds to step S80, where the server-side control unit 70 sets the task flag in the stored data DB (FIG. 5) to ON. Next, in step S82, the extraction unit 58, under the instruction of the server-side control unit 70, extracts keywords based on the keyword DB (FIG. 7) stored in the hard disk 66. As shown in FIG. 7, the keyword DB associates keywords with detailed information, attributes, and confidentiality levels of the keywords. Therefore, the extraction unit 58 focuses on the keyword item in the keyword DB and extracts keywords registered in the keyword DB from the text data.

[0064] For example, the text data is "I'm planning to meet with Ichiro Aoyama of Daitokyo Co., Ltd. at 13:00 on November 20th to discuss the software specifications for Cool Blue Speaker 2." Let's say it was.

[0065] In this case, the extraction unit 58 extracts "Cool Blue Speaker 2", "Software", "Specifications", "Daitokyo Co., Ltd.", and "Aoyama Ichiro" registered in the keyword DB of FIG. 7 as keywords.

[0066] The keyword DB must be created in advance. The contents of the keyword DB can be added or changed as necessary (for example, during maintenance). In addition to attributes such as personal names, company names, and technical terms, as shown in Fig. 7, keywords can also be registered using attributes such as patent information, budget information, and business negotiation information.

[0067] Returning to Fig. 4, in the next step S84, an analysis subroutine for each keyword is executed. Fig. 8 is a flowchart showing specific processing of the analysis subroutine in step S84.

[0068] 8, in step S120, the classification unit 60 acquires the confidentiality levels of keywords from the keyword DB under the instruction of the server-side control unit 70. Specifically, the classification unit 60 acquires "medium" as the confidentiality level of "Cool Blue Speaker 2" from the keyword DB, "medium" as the confidentiality level of "software", "medium" as the confidentiality level of "specifications", "high" as the confidentiality level of "Daitokyo Co., Ltd.", and "high" as the level of "Aoyama Ichiro."

[0069] Next, in step S122, the conversion unit 62, under the instruction of the server-side control unit 70, executes a subroutine to convert the keyword based on the confidentiality acquired in step S120 and store the converted keyword in the flash memory 64.

[0070] Fig. 9 is a flow chart showing a specific process of the subroutine of step S122. As shown in Fig. 9, first, in step S138, the conversion unit 62 selects one keyword from the keywords extracted by the extraction unit 58. In this example, it is assumed that "Daitokyo Co., Ltd." is selected.

[0071] Next, in step S140, the conversion unit 62 judges whether the confidentiality level of the selected keyword is "high". As described above, since "Daitokyo Co., Ltd." has a confidentiality level of "high", the judgment here is affirmative and the process proceeds to step S142. In step S142, the conversion unit 62 executes a subroutine to convert the keyword according to the confidentiality. Specifically, the process is executed according to the flowchart shown in FIG. 10.

[0072] In step S160 in Fig. 10, the conversion unit 62 judges whether or not the selected keyword contains a specific conversion word. Here, the specific conversion word means, for example, a word that is frequently used in company names (such as a joint stock company, a limited liability company, (stock), or (owned)), a word that is frequently used in national or other institutions (such as an organization, a ministry, or an agency), or a word that is frequently used in educational institutions (such as a university or a high school), as defined in the specific conversion word DB in Fig. 11.

[0073] In the case of the selected keyword "Daitokyo Kabushiki Kaisha", since it contains the specific conversion word "Kabushiki Kaisha", the determination in step S160 is affirmative, and the process proceeds to step S162. In step S162, the conversion unit 62 converts the specific conversion word based on the specific conversion word DB. In this case, the "Kabushiki Kaisha" portion of "Daitokyo Kabushiki Kaisha" is converted to "Sha". Next, in step S164, a conversion subroutine other than the specific conversion word is executed.

[0074] Fig. 12 is a flow chart showing the specific processing of the conversion subroutine in step S164. As shown in Fig. 12, in step S190, the conversion unit 62 judges whether the conversion target portion (part other than the specific conversion word) is a place name. Here, the conversion target portion "Daitokyo" includes a place name, but is not the place name itself, so the judgment is negative and the process proceeds to step S194.

[0075] In step S194, the conversion unit 62 judges whether the part to be converted is a name. In this case, since it is not a name, the judgment is denied and the process proceeds to step S198. Then, in step S198, the conversion unit 62 converts the part to be converted, "Daitokyo," into an initial "D." When the process of step S198 ends, the process proceeds to step S165 in FIG. 10.

[0076] In step S165, the conversion unit 62 combines the words converted in steps S162 and S164. Specifically, "D" and "company" are combined to form "D Company."

[0077] Next, in step S168, the conversion unit 62 judges whether or not information is attached to the keyword to be converted, "Daitokyo Co., Ltd." Here, "information is attached" means that information has been entered in the information column of the keyword DB in Fig. 7. In this case, "Daitokyo Co., Ltd." is accompanied by "Electrical Equipment, Shinagawa Ward, Tokyo," so the judgment in step S168 is affirmative, and the process proceeds to step S170.

[0078] In step S170, the conversion unit 62 selects one piece of information that has not yet been selected from the attached information. Next, in step S172, the conversion unit 62 judges whether the confidentiality level of the selected information (for example, "Electricity") is "high" or "medium". Here, if the confidentiality level of "Electricity" is "low", the judgment in step S172 is negative, and the process proceeds to step S182. In step S182, the conversion unit 62 judges whether all the information has been selected. Here, "Shinagawa-ku, Tokyo" has not yet been selected, so the judgment is negative and the process returns to step S170.

[0079] Next, in step S170, the conversion unit 62 selects the unselected information "Shinagawa Ward, Tokyo", and in step S172, judges whether the confidentiality level of "Shinagawa Ward, Tokyo" is "high" or "medium". Here, as shown in the keyword DB in FIG. 7, place names are defined as conforming to the confidentiality level of "low" or the associated keyword, so "Shinagawa Ward, Tokyo" has a confidentiality level of "high" conforming to the keyword "Daitokyo Co., Ltd." Therefore, the judgment in step S172 is affirmative, and the process proceeds to step S174. In step S174, the conversion unit 62 judges whether "Shinagawa Ward, Tokyo" contains a specific conversion word. If the judgment here is negative, the process proceeds to step S180, and a conversion subroutine for converting information is executed. This conversion subroutine in step S180 is basically the same process as that in step S164 described above (FIG. 12).

[0080] That is, in Fig. 12, in step S190, the conversion unit 62 judges whether or not "Shinagawa-ku, Tokyo" is a place name. If the judgment here is positive, in step S192, the conversion unit 62 executes a conversion process based on the place name DB shown in Fig. 13. Specifically, the conversion unit 62 converts "Shinagawa-ku, Tokyo" to "Southern Kanto" by using a conversion method with a confidentiality level of "high". Note that in the place name DB of Fig. 13, when the confidentiality level is "high", the place name is expressed as a position within a relatively wide area, and when the confidentiality level is "medium", the place name is expressed as a position within a narrower area than when the confidentiality level is "high".

[0081] When the process of step S192 ends, the process proceeds to step S182 in Fig. 10. At this stage of step S182, all information (Electrical equipment, Shinagawa-ku, Tokyo) has already been selected, so the determination in step S182 is affirmative and the process proceeds to step S184. In step S184, the conversion unit 62 associates the converted information with the converted keyword (step S165 or S166). In this case, it is "Company D (Electrical equipment, Southern Kanto)". Then, the process proceeds to step S144 in Fig. 9.

[0082] In step S144 in FIG. 9, the converted keyword is stored in area A of the keyword storage DB (see FIG. 14) stored in the flash memory 64. As shown in FIG. 14, the keyword storage DB has storage areas O, B, and C in addition to area A. Raw data of the keyword (pre-conversion keyword) is stored in area O. When the storage process is completed, the process proceeds to step S154, where it is determined whether all of the keywords extracted by the extraction unit 58 have been selected. If the determination here is negative, the process returns to step S138.

[0083] Next, a description will be given of a case where the conversion unit 62 selects "Cool Blue Speaker 2" as the keyword in step S138. In this case, the keyword is "Cool Blue Speaker 2" and the confidentiality level is "medium", so the determination in step S140 is negative, while the determination in step S146 is positive, and the process proceeds to step S148.

[0084] In step S148, a subroutine is executed to convert the keyword according to confidentiality. Specifically, the process of FIG. 10 is executed as in step S142. In the process of FIG. 10, in step S160, the conversion unit 62 judges whether or not the specific conversion word is included in "Cool Blue Speaker 2". Since the judgment here is negative, the process proceeds to step S166 and the conversion subroutine is executed. In the conversion subroutine of this step S166, the process of FIG. 12 is executed as in steps S164 and S180 described above. In FIG. 12, since "Cool Blue Speaker 2" is neither a place name nor a person's name, the judgments of steps S190 and S194 are negative, and the conversion unit 62 performs initial conversion in step S198. In this case, the English notation "Cool Blue Speaker 2" written alongside "Cool Blue Speaker 2" in the keyword DB is converted to initials (capital letters are converted to initials) to convert it to "CBS2".

[0085] When the process of FIG. 12 is completed as described above, the process proceeds to step S168 of FIG. 10. However, since no information is attached to "Cool Blue Speaker 2" in the keyword DB of FIG. 7, the determination in step S168 is negative, and the process proceeds to step S150 of FIG. 9. In step S150, the converted keyword is stored in area B of the flash memory 64 shown in FIG. 14. That is, the conversion unit 62 stores the keyword itself in area O, and stores "CBS2" in area B corresponding to the keyword. When the storage process is completed, the process proceeds to step S154, and it is determined whether all of the keywords extracted by the extraction unit 58 have been selected. If the determination here is negative, the process returns to step S138 again.

[0086] Next, a description will be given of a case where the conversion unit 62 selects the keyword "Aoyama Ichiro" in step S138. In this case, since the confidentiality level of "Aoyama Ichiro" is "high", the determination in step S140 is affirmative, and the process proceeds to step S142.

[0087] In step S142, the process of FIG. 10 is executed as described above. In the process of FIG. 10, step S160 is negative, and the process proceeds to step S166 (process of FIG. 12). In step S190 of FIG. 12, the determination is negative, and the process proceeds to step S194. In step S194, the conversion unit 62 determines whether or not "Aoyama Ichiro" is a name. If the determination here is positive, the process proceeds to step S196. In step S194, "Aoyama Ichiro" is determined to be a name because the attribute of "Aoyama Ichiro" in the keyword DB of FIG. 7 is the name of a business partner.

[0088] In step S196, the conversion unit 62 converts "Aoyama Ichiro" into initials. Note that in step S196, if the confidentiality level of the keyword is "high", both the surname and given name are converted into initials. That is, "Aoyama Ichiro" is converted into "AI". On the other hand, if the confidentiality level of the keyword is "medium", such as "Ueda Saburo" registered in the keyword DB of FIG. 7, only the given name is converted into initials. That is, "Ueda Saburo" is converted into initials into "Ueda S". Note that only the surname may be converted into initials, resulting in "U Saburo".

[0089] When the process of step S196 is completed, the process proceeds to step S168 in FIG. 10. Here, as shown in FIG. 7, the keyword "Aoyama Ichiro" is accompanied by the information "Daitokyo Co., Ltd. Camera AF Motor October 15, 2009 Patent Training Seminar (Tokyo)", so the judgment in step S168 is affirmative, and the process proceeds to step S170. Then, in step S170, for example, the information "Daitokyo Co., Ltd." is selected. As described above, the confidentiality level of "Daitokyo Co., Ltd." is "high", so the judgment in step S172 is affirmative, and the process proceeds to step S174. Then, since "Daitokyo Co., Ltd." includes the specific conversion word "Co., Ltd.", the judgment in step S174 is affirmative, and the conversion of the specific conversion word (step S176) and the conversion of words other than the specific conversion word (step S178) are executed. Note that steps S176 and S178 are the same as steps S162 and S164 described above. If the determination in step S182 is negative, the process returns to step S170.

[0090] Thereafter, steps S170 to S182 are repeated until all the information has been selected. After all the information has been selected, in step S184, the converted information is associated with the converted keyword. Here, for example, it is associated with "AI (camera, AFM, October 15, 2009, T Meeting (Tokyo))". Then, when storage in area A is completed in step S144 of FIG. 9, the process proceeds to step S154, where it is determined whether all the keywords extracted by extraction unit 58 have been selected. If the determination here is negative, the process returns to step S138 again.

[0091] In the above process, if the determination in step S146 in Fig. 9 is negative, that is, if the confidentiality level of the keyword is "low", then in step S152, the keyword is stored as is in area C (and area O). If information is attached to the keyword, that information is also stored in area C. For example, as shown in Fig. 14, the keyword "SVS Co., Ltd." is stored in area C as "SVS Co., Ltd. Machinery Germany Munich".

[0092] Also, in the above process, for example, if the keyword selected in step S138 is "software", software is converted to an initial "SW", and the information <sponge> shown in FIG. 7 is associated with SW without conversion. In this case, the notation <○○> means that the word is treated equally with the keyword. In other words, it means that either "software" or "sponge" is used. Therefore, when the above process is performed on the keyword "software", "SW" and "sponge" are stored equally in area B of flash memory 64. The difference between using "SW" and "sponge" will be described later.

[0093] The above process is also performed for other keywords (here, "specifications"), and if the determination in step S154 in FIG. 9 is affirmative, the process proceeds to step S124 in FIG.

[0094] In step S124, the server-side control unit 70 acquires the weighting for the speaker's attributes. In this case, the weighting (Tw) is acquired from the speaker's job title based on the attribute weighting table shown in Fig. 15(a). For example, if the speaker is Ueda Saburo in Fig. 7, the weighting (Tw) is acquired as "2" for manager (M).

[0095] Next, in step S126, the server-side control unit 70 acquires a weighting for the voice level. In this case, the server-side control unit 70 acquires a weighting (Vw) based on the weighting table for the voice level shown in FIG. 15(b) and the voice level stored in the storage data DB (see FIG. 5). As shown in FIG. 5, when the voice level is 70 db, the weighting (Vw) is 3. Note that the reason why the weighting (Vw) is larger as the voice level is higher is that the higher the voice level, the stronger the request and the higher the importance in many cases.

[0096] Next, in step S128 of FIG. 8, the server-side control unit 70 acquires weights for keywords. In this case, the server-side control unit 70 acquires weights (Kw) based on the keyword weight table shown in FIG. 15(c) and the keywords included in the text data of the stored data DB. In FIG. 15(c), "important", "very important", and "very important" are registered, so if these keywords are included in the text data, a weight (Kw) of 2 or 3 is acquired. Also, in step S128, the server-side control unit 70 determines how many keywords with a confidentiality level of "high" and how many keywords with a confidentiality level of "medium" are included in the text data, and acquires a weight (Cw) for confidentiality of the text data based on the determination result and the keyword confidentiality weight table shown in FIG. 15(d). For example, if the text data contains two keywords with a confidentiality level of "high" and one keyword with a confidentiality level of "medium", the server-side control unit 70 obtains Cw=8 (=3×2+2×1).

[0097] When the process of step S128 in Fig. 8 is completed, the process proceeds to step S86 in Fig. 4. In step S86, the server-side control unit 70 calculates the task priority (Tp) and registers it in the stored data DB (Fig. 5). Specifically, the server-side control unit 70 calculates the task priority (Tp) using the following formula (1). Tp = Uvw × Vw + Utw × Tw +Ufw×Fw+Ukw×Kw+Ucw×Cw …(1)

[0098] In addition, Uvw, Utw, Ufw, Ukw, and Ucw in the above equation (1) are weighting coefficients that take into account the importance of each weight (Vw, Tw, Fw, Kw, Cw), and these weighting coefficients can be set by a user or the like via the setting unit 74.

[0099] Next, the process proceeds to step S88 in FIG. 4, where the server-side control unit 70 registers the keywords contained in the text data in the keyword recording DB shown in FIG. 16. The keyword recording DB in FIG. 16 is created, for example, on a weekly, monthly, or yearly basis. The keyword recording DB in FIG. 16 records related information such as keywords used simultaneously with the keywords contained in the text data (called registered keywords), the speaker of the registered keywords, the date and time when the registered keywords were spoken, and the location. The number of times the registered keywords are associated with related information is recorded as the degree of association. Furthermore, the number of times the registered keywords are uttered is recorded as the frequency of occurrence. The search frequency item in the keyword recording DB in FIG. 16 will be described later.

[0100] After the process of step S88 is completed, the process returns to step S70.

[0101] (If the determination in step S78 is negative (if it is not a task)) Next, a case where the determination in step S78 is negative will be described. If the determination in step S78 is negative, the process proceeds to step S90, where the server-side control unit 70 turns off the task flag. Next, in step S92, the server-side control unit 70 determines whether the speaker is the user himself or herself. If the determination here is positive, the process proceeds to step S94, where it is determined whether the words uttered by the user are commands. Here, for example, as shown in the command DB in FIG. 17, the word "task list" is a command to display a task list, the word "voice recording text" is a command to display a voice recording list, and the word "conversion" is a command for conversion processing. Note that this command DB is stored in the flash memory 28 on the mobile terminal 10 side or the hard disk 66 on the server 50 side. In this command DB, for example, when the user's voice is "task list," it is defined that a task list as shown in FIG. 18(a) is displayed. Note that the task list will be described in detail later. Also, in the command DB, it is defined that when the user's voice is "voice recording text," a voice recording list as shown in FIG. 18(b) is displayed. The voice recording list will be described in detail later.

[0102] 4, if the determination in step S94 is negative, the process returns to step S70, but if the determination in step S94 is positive, the process proceeds to step S96, where the server-side control unit 70 executes a subroutine for executing processing according to the command. Specifically, the processes in Figs. 19, 20, and 21 are executed simultaneously in parallel.

[0103] First, the process on the server 50 side will be described with reference to the flowchart in Fig. 19. On the server 50 side, in step S202, the server-side control unit 70 determines whether the command is a display request. In this case, as described above, the commands "task list" and "voice recording text" correspond to the display request.

[0104] Next, in step S204, the server-side control unit 70 extracts data necessary for displaying according to the command from the flash memory 64. For example, if the command is "task list," text data to be displayed in the task list (text data with the task flag turned on in FIG. 5) is extracted from the flash memory 64. Note that the text data with the task flag turned on in this case includes not only text data converted from voice data, but also text data directly input from the text data input unit 44. Note that the task flag of directly input text data is turned on and off by the same process as that shown in FIG. 6 described above.

[0105] Next, in step S206, the server-side control unit 70 acquires the current location of the user. In this case, the server-side control unit 70 acquires location information detected by the location detection unit 22 of the mobile terminal 10 via the terminal-side control unit 30, the communication units 32 and 52, etc.

[0106] Next, in step S208, the server-side control unit 70 judges whether the location is a place where security can be ensured based on the acquired location information (current location). Here, an example of a place where security can be ensured is within a company. The location of the company is registered in the following manner.

[0107] For example, a user connects the portable terminal 10 to a PC (Personal Computer) via a USB or the like, and starts a dedicated application using map information on the PC. The application then registers the location of the company by specifying the company's address. The address is specified by a drawing operation using a mouse or the like. The company's location is expressed as an area of ​​a predetermined size. Therefore, the company's location can be expressed by two diagonal points (latitude, longitude) of a rectangular area, as shown in the security ensureable range DB of FIG. 22. The security ensureable range DB of FIG. 22 is stored in the hard disk 66 of the server-side control unit 70.

[0108] That is, in step S208, the server-side control unit 70 refers to the secure range DB of FIG. 22, and if the user is within the range, it is determined that the user is located within a place where security can be ensured.

[0109] If the determination in step S208 is positive, the process proceeds to step S210. In this step S210, the server-side control unit 70 obtains conversion words associated with the keywords included in the extracted data from areas O, A, B, and C, and proceeds to step S214. On the other hand, if the determination in step S208 is negative, the process proceeds to step S212. In this step S212, the server-side control unit 70 obtains conversion words associated with the keywords included in the extracted data from areas A and B, and proceeds to step S214.

[0110] In step S214, the server-side control unit 214 transmits the extracted data and the conversion word associated with the keyword to the mobile terminal 10 via the communication unit 52.

[0111] If the determination in step S202 is negative, that is, if the command is a command other than a display request, the server-side control unit 70 performs processing according to the command in step S216.

[0112] Next, the process in the mobile terminal 10 will be described with reference to Fig. 20. In step S220 in Fig. 20, the terminal control unit 30 judges whether data has been transmitted from the server side. In this step, the judgment is made positive after step S214 in Fig. 19 is executed.

[0113] Next, in step S221, the terminal-side control unit 30 judges whether or not the converted words in the areas A, B, and C have been transmitted. Here, the judgment is YES if the process goes through step S210 in FIG. 19, and the judgment is NO if the process goes through step S212.

[0114] If the determination in step S221 is positive, in step S222, the terminal-side control unit 30 converts the keywords included in the extracted data with the conversion words in areas A, B, and C. That is, for example, if the extracted data is "I'm planning to meet with Ichiro Aoyama of Daitokyo Co., Ltd. at 13:00 on November 20th to discuss the software specifications for Cool Blue Speaker 2." In this case, using the conversion words for areas A, B, and C, "I'm planning to meet with AI (camera, AFM, T-kai (Tokyo)) from D Company (Electrical Equipment, Southern Kanto) on November 20th at 1pm about SWSP for CBS2." is converted to:

[0115] On the other hand, if the determination in step S221 is negative, in step S223, the terminal side control unit 30 converts the extracted data with the conversion word in area B and deletes the word in area A. In this case, the extracted data is "I'm planning to meet with about SWSP on CBS2 on November 20th at 1pm." In this manner, in this embodiment, the display mode of data is changed depending on whether security is ensured or not.

[0116] After the process of step S222 or step S223 is performed as described above, the process proceeds to step S224, and the terminal-side control unit 30 executes a process of displaying the converted text data at a predetermined position on the display unit 14. In this display, the tasks may simply be displayed in order of the time (date and time) of the task being closest to the current time (date and time), but in this embodiment, instead, the tasks are displayed in order of the task priority. This reduces the user's overlooking of important tasks, and enables the user to prioritize high-priority tasks when making a schedule even if multiple schedules are double-booked. In the case of double-booking, the terminal-side control unit 30 may issue a warning via the warning unit 18, or, in the case where a person involved in a schedule with a lower priority is included in a task, the terminal-side control unit 30 may automatically request a change request notification for the schedule of the task from that person by email. However, the display is not limited to the case of high task priority as described above, and it is of course possible to display the tasks in order of date and time. In addition, the tasks may be displayed in order of date and time, and the font, color, size, etc. of the tasks with high task priority may be changed to make them stand out. Furthermore, tasks may be arranged in descending order of task priority, and tasks with the same task priority may then be displayed in chronological order.

[0117] As described above, the processing of FIG. 19 and FIG. 20 results in the screen display as shown in FIG. 18(a) and FIG. 18(b). The recorded voice list of FIG. 18(b) has a task item. The user can switch the task flag on and off by touching the task item on the touch panel. In this case, the server-side control unit 70 changes the task flag in FIG. 5 when it recognizes the user's task flag switching operation. This allows the user to manually change the task flag even if the on / off of the task flag is different from the user's recognition as a result of the processing of FIG. 6. In addition, when the user turns on a task flag, the server-side control unit 70 may automatically turn on the task flag for text data similar to the text data of the task.

[0118] 20, the terminal-side control unit 30 transmits the current location acquired by the location detection unit 22 to the server-side control unit 70, and converts and displays the text data using the conversion word transmitted from the server-side control unit 70. Therefore, in this embodiment, it can be said that the terminal-side control unit 30 restricts the display on the display unit 14 according to the current location acquired by the location detection unit 22.

[0119] Next, a process performed in parallel with the process of FIG. 20 will be described with reference to FIG. 21. In FIG. 21, in step S232, the terminal-side control unit 30 judges whether or not the document conversion button has been pressed by the user. The document conversion button is the button displayed in the upper right corner in FIG. 18(a) and FIG. 18(b). The user presses the document conversion button by operating the touch panel or the keyboard. If the judgment in step S232 is positive, the process proceeds to step S234, and if not, the process proceeds to step S238.

[0120] In step S234, the terminal-side control unit 30 judges whether or not a convertible keyword is displayed. Here, a convertible keyword means a keyword in which multiple conversion words are associated with one keyword, such as "SW" and "sponge" shown in FIG. 14. Therefore, if such a keyword is included in the text data displayed on the display unit 14, the judgment here is affirmative, and the process proceeds to step S236. On the other hand, if the judgment in step S234 is negative, the process proceeds to step S238.

[0121] When the process proceeds to step S236, the terminal control unit 30 converts the keyword. "I'm planning to meet with AI (camera, AFM, T-kai (Tokyo)) from D Company (Electrical Equipment, Southern Kanto) on November 20th at 1pm about SWSP for CBS2." In the sentence, "SW" can be converted to "sponge". Therefore, the terminal control unit 30 converts the "SW" to "sponge". "I'm planning to meet with AI (camera, AFM, T-kai (Tokyo)) of D Company (electrical equipment, southern Kanto) on November 20th at 1pm about the Sponge SP of CBS2." and convert it and display it.

[0122] Even if a user cannot recall software when they see "SW," they can press the document conversion button and see the word "sponge" to recall software through the association of sponge → soft → soft. Note that, when a user sees the word sponge for the first time, they may not be able to make such an association, but if the method of association is made known within the company, recalling software will be easy.

[0123] Next, in step S238, the terminal-side control unit 30 judges whether or not the display before conversion button (see FIG. 18(a) and FIG. 18(b)) has been pressed. The user presses the display before conversion button when he / she wants to see the text without the keyword being converted. If the judgment here is negative, the process returns to step S232, but if the judgment here is positive, the process proceeds to step S240. In step S240, the terminal-side control unit 30 acquires the user's current location, and in step S242, the terminal-side control unit 30 judges whether or not the current location is a place where security can be ensured. If the judgment here is negative, that is, if the user is in a place where security cannot be ensured, it is necessary to restrict the user from seeing the text before conversion. Therefore, in step S252, the user is notified that the text cannot be displayed, and the process returns to step S232. As a method of notification in step S252, a display on the display unit 14, a warning via the warning unit 18, or the like can be adopted.

[0124] If the determination in step S242 is positive, the process proceeds to step S244, where the terminal-side control unit 30 displays questions (questions that the user can easily answer) on the display unit 14. The questions are assumed to be stored in the hard disk 66 on the server 50 side, and the terminal-side control unit 30 reads the questions from the hard disk 66 and displays them on the display unit 14. The questions and example answers may be registered in advance by the user, for example.

[0125] Next, in step S246, the terminal control unit 30 judges whether or not the user has input an answer by voice to the input unit 12. If the judgment here is positive, the terminal control unit 30 judges in step S248 whether or not it is the user's voice and whether or not the answer is correct. Whether or not it is the user's voice is judged using the results of analyzing the voice in the voiceprint analysis unit 55 on the server 50 side described above. If the judgment here is negative, in step S252, the user is notified that it is not possible to display. On the other hand, if the judgment in step S248 is positive, the process proceeds to step S250, where the keyword is converted to its pre-conversion state in the conversion word in area O and displayed. Specifically, the sentence as it was input by voice, that is, in the above example, "I'm planning to meet with Ichiro Aoyama of Daitokyo Co., Ltd. at 13:00 on November 20th to discuss the software specifications for Cool Blue Speaker 2." Then, the process proceeds to step S232, and the above process is repeated. Although the above describes a case where the user answers the question by voice, the present invention is not limited to this, and the answer may be input from a keyboard or the like. In this case, the terminal-side control unit 30 may determine whether or not to display the state before conversion based on the result of biometric authentication such as fingerprint authentication in addition to the answer to the question.

[0126] When the process of step S96 in FIG. 4 ends in this manner, the process returns to step S70.

[0127] On the other hand, if the determination in step S92 in FIG. 4 is negative, that is, if the speaker is not the user, the process proceeds to step S100, where the terminal-side control unit 30 displays information about the speaker. Here, the terminal-side control unit 30 performs display based on information received from the server-side control unit 70. Specifically, if the speaker is Aoyama Ichiro, the terminal-side control unit 30 receives that information from the server-side control unit 70 and displays it as "Aoyama Ichiro." If information associated with Aoyama Ichiro is received, that information may also be displayed. If a task related to Aoyama Ichiro is received from the server-side control unit 70, that task may also be displayed.

[0128] In this way, for example, when Mr. Ichiro Aoyama calls out to the user, such as "Good morning," the name, related information, tasks, etc. can be displayed on the display unit 14. This can help the user to remember a person's name or information, or things to do related to that person.

[0129] Next, in step S102, the server-side control unit 70 judges whether or not a word registered in the ambiguous word DB shown in Fig. 23 has been uttered. If the judgment here is negative, the process returns to step S70, but if the judgment here is positive, the process proceeds to step S104.

[0130] In step S104, the server-side control unit 70 and the terminal-side control unit 30 execute processing corresponding to the uttered word based on the ambiguous word DB of Fig. 23. Specifically, when "that incident" or "that incident" is uttered, the server-side control unit 70 refers to the keyword record DB, extracts keywords that are included in the related information of the speaker and have a frequency of occurrence higher than a predetermined threshold, and transmits the extracted keywords to the terminal-side control unit 30. The terminal-side control unit 30 then displays the received keywords on the display unit 14. For example, when the speaker is Manager Yamaguchi and the threshold for frequency of occurrence is 10, the keyword "Project A" in the keyword record DB of Fig. 16 is displayed on the display unit 14. Also, as shown in FIG. 23, when "(place name) matter", for example, "Hokkaido matter" is said, a keyword in which the speaker is included in the related information and the position (latitude, longitude) where the voice data was input is within a predetermined range (for example, within Hokkaido), or a keyword in which the speaker is included in the related information and the word "Hokkaido" is included in the related information is extracted and displayed on the display unit 14. Furthermore, when "XX month XX day matter" is said, for example, a keyword in which the speaker is included in the related information and the date and time when the voice data was input matches XX month XX day, or a keyword in which the speaker is included in the related information and the word "XX month XX day" is included in the related information is extracted and displayed on the display unit 14. Furthermore, there are cases where it is easy to estimate from the keyword record DB of FIG. 16 that a certain person will speak at a certain time (date and time). In such a case, a keyword related to the speaker and the current time may be displayed.

[0131] In step S104, by executing the above-mentioned process, even if the speaker asks an ambiguous question, it is possible to automatically determine what the question is asking and display it to the user. Note that in step S104, every time a keyword is displayed, the server-side control unit 70 updates the search frequency of the keyword record DB. This search frequency can be used, for example, in cases where a keyword with a higher search frequency is preferentially displayed.

[0132] Next, the process of erasing data acquired by the mobile terminal 10 and the server 50 will be described with reference to FIGS.

[0133] (Data deletion process (part 1: Deleting converted data)) FIG. 24 shows a flow chart of a process of erasing information acquired by the mobile terminal 10 from the server 50. As shown in FIG. 24, the terminal control unit 30 judges in step S260 whether a certain time (for example, 2 to 3 hours) has passed since the data was acquired. If the judgment here is positive, the process proceeds to step S262, where the terminal control unit 30 erases the text data (including the pre-conversion word and the post-conversion word) stored in the flash memory 28. On the other hand, even if the judgment here is negative, the terminal control unit 30 judges in step S264 whether the user has moved from inside the company to outside the company. Then, if the judgment here is positive, the process proceeds to step S262, where the data is erased in the same manner as described above. Note that if the judgment here is negative, the process returns to step S260. In this way, if a certain time has passed since the data was acquired, or if security cannot be ensured, the data is erased, whereby leakage of important data, etc. can be prevented. In the above, the case where all the text data is erased has been described, but this is not limiting, and in step S262, only the most important data may be erased. For example, only the data in area A and the data in area O may be erased.

[0134] In the process of FIG. 24, if the user (mobile terminal 10) is located outside the company from the beginning, the converted data may be erased from the flash memory 28 immediately after being displayed on the display unit 14.

[0135] (Data deletion process (part 2: Deleting voice data)) The server-side control unit 70 executes the deletion process of Fig. 25 for each voice data. In step S270 of Fig. 25, the server-side control unit 70 judges whether the text data generation unit 54 has (could) convert the voice data into text data. If the judgment here is negative, the process proceeds to step S280, but if the judgment here is positive, the process proceeds to step S272, where the server-side control unit 70 acquires the name of the person who spoke the voice data. Here, the server-side control unit 70 acquires the name of the person who spoke the voice data from the voiceprint analysis unit 55, and proceeds to step S274.

[0136] In step S274, the server-side control unit 70 judges whether the person who spoke is other than the user himself / herself. If the judgment here is positive, the server-side control unit 70 deletes the voice data converted into text data in step S276. On the other hand, if the judgment in step S274 is negative, that is, if the voice data is the user's own voice data, the server-side control unit 70 proceeds to step S278, where the voice data is deleted after a predetermined time has elapsed, and all the processing in FIG. 25 is terminated.

[0137] On the other hand, if the determination in step S270 is negative and the process proceeds to step S280, the server-side control unit 70 enables the voice data to be played back. Specifically, the server-side control unit 70 transmits the voice data to the flash memory 28 of the mobile terminal 10. In step S280, a warning is issued to the user via the warning unit 18 that the voice data could not be converted into text data. Based on this warning, if the user inputs an instruction to play back the voice data from the input unit 12 of the mobile terminal 10, the voice data stored in the flash memory 28 is played back via the playback unit 16.

[0138] Next, in step S282, the server-side control unit 70 erases the voice data transmitted to the flash memory 28 (that is, the voice data reproduced by the reproduction unit 16), and the entire process of FIG. 25 ends.

[0139] By executing the voice data deletion process in the above manner, it is possible to reduce the amount of voice data stored in the server 50, and therefore it is possible to reduce the storage capacity of the flash memory 64 of the server 50. Also, by deleting voice data of anyone other than the user immediately after it is converted into text data, it is possible to take privacy into consideration.

[0140] (Data Deletion Process (Part 3: Task Deletion)) The server-side control unit 70 deletes the task according to the following rules. (1) If the task is about an external meeting In this case, the task is erased when the current location detected by the location detection unit 22 matches the conference location specified in the task and the current time detected by the time detection unit 24 has passed the conference start time specified in the task. If the current time has passed the conference start time but the current location does not match the conference location, the server-side control unit 70 causes the warning unit 18 to issue a warning to the user via the terminal-side control unit 30. This makes it possible to prevent the task from being forgotten to be executed. Furthermore, without being limited to this, for example, a warning may be issued a predetermined time before the task (e.g., 30 minutes before). This makes it possible to prevent the task from being forgotten to be executed. (2) If the task is about an internal meeting In this case, a position detector capable of detecting entry into a conference room, such as an RFID, is employed as the position detector 22, and the task is erased when the current position detected by the position detector 22 matches the conference room specified in the task and the current time detected by the time detector 24 is past the conference start time specified in the task. Even in this case, a warning can be used in conjunction as in (1) above. (3) The task is about shopping and the location of the shopping is specified. In this case, the task is deleted when the current location detected by the location detection unit 22 matches the location specified in the task and a voice such as "Thank you" is input from the voice input unit 42, or purchase information is input wirelessly from the POS register terminal to the input unit 12. Note that, in addition to input from the POS register terminal, for example, if the portable terminal has an electronic money function, the task may be deleted when payment is made using that function. (4) Any other time-specific tasks In this case, when the current time detected by the time detection unit 24 passes the execution time defined in the task, the task is deleted.

[0141] As described above, this embodiment includes the communication unit 52 to which information is input, the extraction unit 58 to extract a predetermined keyword from the data input to the communication unit 52, the classification unit 60 to classify the keywords extracted by the extraction unit 58 into keywords with a confidentiality level of "high" and keywords with a confidentiality level of "medium", and the conversion unit 62 to convert the keywords with a confidentiality level of "high" using a predetermined conversion method and convert the keywords with a confidentiality level of "medium" using a conversion method different from that used for the keywords with a confidentiality level of "high". In this way, by classifying keywords according to confidentiality level and performing different conversions according to each level, it becomes possible to display data taking into account the confidentiality level. This makes it possible to improve usability.

[0142] Furthermore, in this embodiment, the communication unit 52, which communicates with the portable terminal 10, transmits the result of the conversion performed by the conversion unit 62 to the portable terminal 10, so that the portable terminal 10 can display data that takes into consideration the confidentiality level without processing the data.

[0143] Furthermore, this embodiment is provided with a text data generation unit 54 that generates text data from voice data, and the extraction unit 58 extracts keywords from the text data generated by the text data generation unit 54, making it easy to extract keywords.

[0144] In this embodiment, since the keyword is converted to initials, each keyword can be easily converted without creating a special conversion table for each keyword. In addition, when the keyword is a name, if the confidentiality level is "high", both the last name and the first name are converted to initials, and if the confidentiality level is "medium", either the last name or the first name is converted to initials, so that it is possible to perform display according to the confidentiality level. Furthermore, when the keyword is a place name, if the confidentiality level is "high", it is converted to information on a specified area (location information within a wide range), and if the confidentiality level is "medium", it is converted to information on an area narrower than the specified area (location information within a narrow range), so that it is also possible to perform display according to the confidentiality level.

[0145] In this embodiment, the device includes a position detection unit 22 that detects position information, an input unit 12 that performs input, a display unit 14 that displays information related to the input, and a terminal-side control unit 30 that restricts display on the display unit 14 according to the position detected by the position detection unit 22. In this way, by restricting display according to the position, it is possible to perform display that takes security into consideration, and ultimately to improve usability.

[0146] In addition, in this embodiment, when it is determined that security is not maintained based on the output of the position detection unit 22, the terminal-side control unit 30 restricts the display on the display unit 14, so that display restrictions can be implemented with appropriate consideration given to security. In this embodiment, when it is determined that security is maintained based on the output of the position detection unit 22, at least a part of the restrictions on the display on the display unit 14 is lifted, so that also from this point of view, display restrictions can be implemented with appropriate consideration given to security.

[0147] Furthermore, since the personal assistant system 100 of this embodiment includes the portable terminal 10 that imposes display restrictions in consideration of security as described above, and the server 50 that imposes display restrictions on at least a portion of the data input from the portable terminal 10, the display unit 14 of the portable terminal 10 can display data with display restrictions imposed thereon, even if the portable terminal 10 does not impose display restrictions on at least a portion of the data. This reduces the processing load on the portable terminal 10, and as a result, the portable terminal 10 can be simplified and made smaller and lighter.

[0148] In addition, this embodiment includes the display unit 14 that displays text data, the voice input unit 42 that inputs voice, and the terminal-side control unit 30 that displays information related to the voice on the display unit according to the analysis result of the voiceprint analysis unit 55 that analyzes the voiceprint of the voice. As a result, when a person utters a voice such as "Good morning" at step S100 in FIG. 4, the information of the person (such as the name, other registered information, or tasks to be performed for the person) can be displayed on the display unit 14. This allows the user to remember the person by looking at the display unit 14 even if the user has forgotten who uttered the voice. In this way, this embodiment can provide a user-friendly personal assistant system 100 and a portable terminal 10.

[0149] In this embodiment, the terminal-side control unit 30 and the server-side control unit 70 display information related to a predetermined word (such as "that matter" or "Hokkaido matter") included in the voice data on the display unit 14 according to the analysis result of the voiceprint analysis unit 55. Therefore, even if an ambiguous question such as "that matter" or "Hokkaido matter" is asked, the user can remember the matter by checking the display unit 14. From this point of view, this embodiment can provide a user-friendly personal assistant system 100 and a portable terminal 10. In this embodiment, information related to a predetermined word (such as "Hokkaido matter") is selected according to the frequency of inputting the predetermined word (such as "Hokkaido") into the input unit and displayed on the display unit 14 (step S104 in FIG. 4), so that appropriate information can be displayed.

[0150] Furthermore, in step S104 in FIG. 4, information according to the position at which the voice data was input is displayed on the display unit 14, so that appropriate information display is also possible in this respect.

[0151] Also, in step S104 of FIG. 4, information corresponding to the time when the voice data was input (such as information input within a predetermined time from the time when the voice data was input) is displayed on the display unit 14, so that appropriate information can be displayed in this respect as well.

[0152] In addition, this embodiment includes a voice input unit 42 for inputting voice, a text data generation unit 54 for generating text data based on the voice data input to the voice input unit 42, a voiceprint analysis unit 55 for analyzing voiceprint data of the voice data input to the voice input unit 42, and an erasure unit 76 for erasing the voice data after the text data is generated by the text data generation unit 54 in accordance with the analysis result by the voiceprint analysis unit 55. This makes it possible to reduce the storage capacity required for the flash memory 64 by erasing the voice data after the text data is generated. In addition, this embodiment erases the voice data in accordance with the analysis result by the voiceprint analysis unit 55, thereby making it possible to realize good usability that takes privacy into consideration by erasing the voice data of a specific person.

[0153] In this embodiment, the device includes a communication unit 52 to which information is input, an extraction unit 58 to extract predetermined keywords from the data input to the communication unit 52, a classification unit 60 to classify the keywords extracted by the extraction unit 58 into keywords with a confidentiality level of "high" and keywords with a confidentiality level of "medium", and a conversion unit 62 to convert keywords with a confidentiality level of "high" using a predetermined conversion method and convert keywords with a confidentiality level of "medium" using a conversion method different from that used for keywords with a confidentiality level of "high". In this way, by classifying keywords according to confidentiality level and performing different conversions according to each level, it becomes possible to display data taking the confidentiality level into consideration.

[0154] Furthermore, in this embodiment, the voiceprint analysis unit 55 analyzes whether the voiceprint data of the voice data is that of a registered user, and the erasure unit 76 erases voices other than those of the user, thereby effectively reducing the storage capacity of the flash memory 64 and further enhancing consideration for privacy.

[0155] In this embodiment, the erasing unit 76 determines the time from analysis to erasure between the user's voice and the voice of a person other than the user (steps S276, S278). This allows the user's voice to be erased after a predetermined time, further reducing the storage capacity.

[0156] In this embodiment, when the text data generating unit 54 cannot generate text data from the voice data, the warning unit 18 issues a warning, so that the user can recognize that the text data could not be generated from the voice data. Also, when the text data generating unit 54 cannot generate text data from the voice data (when step S270 is negative), the playback unit 16 plays back the voice data in response to a user instruction, so that the user can check the content that could not be made into text data by playing back the voice data.

[0157] Further, according to this embodiment, the display unit 14 for displaying, the voice input unit 42 for inputting voice, the weighting unit 56 for weighting based on at least one of the volume, frequency and meaning of the input voice, and the control units 70, 30 for changing the display mode of the task on the display unit based on the voice input by the voice input unit 42 and the weighting by the weighting unit 56. As a result, the display mode of the task on the display unit 14 is changed based on the weighting performed by the weighting unit 56 according to the input method of the voice data, the contents of the voice data, etc., so that a display mode according to the weight (importance) of the voice data can be realized. As a result, it is possible to improve usability.

[0158] Furthermore, according to this embodiment, the weighting unit 56 uses at least the frequency of the voice data to identify the person who made the sound and assigns weighting according to that person (job title in this embodiment), thereby enabling appropriate weighting of the importance of the voice data.

[0159] Furthermore, according to this embodiment, the weighting unit 56 performs weighting in accordance with confidentiality based on the meaning of the voice, so that appropriate weighting can be performed regarding the importance of the voice data.

[0160] In addition, in this embodiment, if the voice input from the voice input unit 42 contains date information, the tasks can be displayed based on the date information, so that the function of a normal schedule can also be satisfied. In addition, in this embodiment, the tasks are displayed taking into consideration information about the time detected by the time detection unit 24 or the date information of the calendar unit 26, so that it is possible to display the tasks to be performed in an order such as the order closest to the current time or the order furthest from the current time.

[0161] In addition, in this embodiment, since the text data generating unit 54 that converts the voice input from the voice input unit 42 into text data is provided, the weighting unit 56 can weight the text data. This makes it possible to perform weighting more easily than in the case of handling voice data.

[0162] Furthermore, in this embodiment, the display order, color, display size, display font, and the like are changed based on the weighting results, so that the weighting results can be expressed in various ways.

[0163] Furthermore, in this embodiment, the display mode on the display unit is changed according to the output of the position detection unit 22 which detects the position. In other words, when it is determined that a task has been executed based on the current position, the task is not displayed (deleted), which makes it possible to reduce memory capacity.

[0164] Furthermore, in this embodiment, whether or not the voice data is a task is determined based on whether or not it contains standard words, and this determination result is used to decide whether or not to display it on the display unit 14, so that it is possible to automatically determine whether or not the voice data is a task, and also to automatically decide whether or not to display it on the display unit.

[0165] In addition, in this embodiment, a setting unit 74 is provided in the server 50 to enable the user to set the weighting, so that the user can set the weighting according to his or her own preferences.

[0166] Further, according to this embodiment, the system includes a voice input unit 42 for inputting voice, a text data generating unit 54 for converting the input voice into text data, and a server-side control unit 70 for starting conversion by the text data generating unit 54, i.e., starting recording and converting to text data, when the voice input unit 42 inputs a specific frequency. Therefore, when a person speaks and a voice of a specific frequency is input, recording and conversion to text data are started based on the input of the voice (see FIG. 2(a)), so that recording and conversion to text data can be started automatically. This simplifies the user's operation and improves usability.

[0167] In addition, in this embodiment, since conversion to text data can be started when the voice input unit 42 inputs a frequency related to a telephone call, for example, it is possible to record the voice of a telephone call and convert it to text data from the moment the telephone rings. This makes it possible to record and convert a telephone conversation into text data without missing anything.

[0168] In addition, in this embodiment, since recording and conversion to text data can be started at an appropriate timing, for example, when the date and time of a meeting is reached, based on a task, the user's operation can be simplified and usability can be improved. Also, since recording and conversion to text data can be performed according to the end time of a meeting (see FIG. 2(c)), it is possible to automatically start recording voice data and converting it to text data during a time period when the most important things are likely to be discussed in the meeting.

[0169] In addition, in this embodiment, recording and conversion to text data can be started at an appropriate time based on the user's biometric information (see FIG. 2(d)), which also simplifies user operations and improves usability.

[0170] Furthermore, in this embodiment, recording and conversion to text data can be started when the current time reaches a predetermined time (see FIG. 2(b)), which also simplifies user operations and improves usability.

[0171] In addition, in this embodiment, since conversion by the text data generating unit 54 can be prohibited according to the detection result of the position detecting unit 22, recording can be automatically prohibited in cases where there is a problem with recording, such as an external conference. This makes it possible to further improve usability.

[0172] In the above embodiment, the confidentiality level is determined for each word, but this is not limited to the above. For example, the classification unit 60 may classify words used in business as words with a high confidentiality level and words used in private as words with a low confidentiality level.

[0173] In the above embodiment, a case where a keyword is converted and displayed when the current location detected by the location detection unit 22 of the mobile terminal 10 is a location where security is not maintained, that is, a case where the display on the display unit 14 is restricted, has been described, but the present invention is not limited to this. For example, when the time detected by the time detection unit 24 is a predetermined time (for example, during working hours), the display on the display unit 14 may be restricted. Even in this way, it is possible to perform display that takes security into consideration, as in the above embodiment. In the case of performing such control, instead of acquiring the current location of the user in step S206 of FIG. 19, the current time may be acquired, and instead of judging whether the location is a place where security can be ensured in step S208, it may be judged whether the time is a place where security can be ensured.

[0174] In the above embodiment, the determination of whether the voice data is a task is made based on the presence or absence of date and time information and the type of ending of the voice data, but this is not limited to the above, and the task determination may also be made based on, for example, the intonation of the voice data.

[0175] In the above embodiment, the case where words with a confidentiality level of "high" and words with a confidentiality level of "medium" are converted into their superordinate initials is described, but the present invention is not limited to this. For example, a converted word for each word may be defined in the keyword DB. In this case, for example, as a converted word for the keyword "camera", a superordinate concept of camera, "precision equipment" and a subordinate concept, "photography device", can be defined. In this case, if "camera" has a confidentiality level of "high", it can be converted into "precision equipment", and if "camera" has a confidentiality level of "medium", it can be converted into "photography device". In this way, by converting into a superordinate concept word and a medium concept word according to the confidentiality level, it is possible to perform display taking into consideration the security level. In addition, when monetary information such as a budget is registered in the keyword DB, a superordinate concept of the monetary information expressed in digits may be defined.

[0176] In the above embodiment, the voice is in Japanese, but it may be in a foreign language such as English. In a foreign language (e.g., English), it may be determined whether or not the voice is a task based on the presence or absence of a predetermined word or a predetermined syntax.

[0177] In the above embodiment, a case has been described in which a flash memory 28 is installed in order to make the portable terminal 10 smaller and lighter. However, in addition to or instead of this, a storage device such as a hard disk may also be installed in the portable terminal 10.

[0178] In the above embodiment, the case where the mobile terminal 10 is connected to an external PC and the setting is performed on the external PC when setting the company location, etc., has been described. However, this is not limited to this, and for example, the company location may be registered in advance on the hard disk 66 of the server 50, and the company location may be downloaded from the hard disk 66. Also, for example, an application for setting the company location, etc. may be installed on the mobile terminal 10, so that the company location, etc. can be set on the mobile terminal 10.

[0179] In the above embodiment, the task priority is calculated based on the above formula (1), but the present invention is not limited to this, and other formulas may be used to calculate the task priority. For example, the weights may be added or multiplied. Furthermore, the present invention is not limited to the case where the task priority is calculated using the above formula (1), and the task priority may be determined in descending order of the selected weight by selecting one of the weights. In this case, the user may be able to set which weight is used to determine the task priority.

[0180] In the above embodiment, the case where the initialized keyword (for example, "SW" in software) and the image-based keyword (for example, "Sponge" in software) are displayed first is described, but the present invention is not limited to this, and the image-based keyword may be displayed first. Also, the initialized keyword and the image-based keyword may be displayed simultaneously.

[0181] In the above embodiment, when the voice of a person other than the user is input to the input unit 12, the name and information of the speaker are displayed, but the present invention is not limited to this. For example, an image related to the speaker, such as a facial photograph of the speaker, may be displayed. In this case, it is necessary to store the image in the hard disk 66 of the server 50, for example, and to register the image in the information section of the keyword DB.

[0182] In the above embodiment, the weight may be determined based on the degree of intimacy with the user. In this case, for example, a person who has a relatively large number of voice inputs or a person who has a mobile terminal and has many opportunities to approach the user may be determined to have a high degree of intimacy.

[0183] The configuration described in the above embodiment is merely an example. That is, at least a part of the configuration of the server 50 described in the above embodiment may be provided on the mobile terminal 10 side, or at least a part of the configuration of the mobile terminal 10 described in the above embodiment may be provided on the server 50 side. Specifically, for example, the voiceprint analysis unit 55 and the text data generation unit 54 of the server 50 may be provided on the mobile terminal 10.

[0184] In the above embodiment, the present invention has been described mainly in terms of its use for business purposes, but it may also be used for private purposes, or it may be used for both private and business purposes.

[0185] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this embodiment and can be modified in various ways without departing from the scope of the present invention. [Explanation of symbols]

[0186] 10...portable terminal, 12...input unit, 14...display unit, 16...playback unit, 18...warning unit, 20...biometric information input unit, 22...position detection unit, 24...time detection unit, 26...calendar unit, 28...flash memory, 30...terminal side control unit, 32...communication unit, 50...server, 52...communication unit, 54...text data generation unit, 55...voiceprint analysis unit, 56...weighting unit, 58...extraction unit, 60...classification unit, 62...conversion unit, 64...flash memory, 66...hard disk, 70...server side control unit, 72...change unit, 74...setting unit.

Claims

[Claim 1] an input section for inputting information; an extraction unit that extracts a predetermined word from the information input to the input unit; a classification unit that classifies the words extracted by the extraction unit into first words and second words; a conversion unit that converts the first word by a first conversion method and converts the second word by a second conversion method different from the first conversion method; a determination unit for determining whether or not to display the word converted by the first conversion method according to a time or a user's location; An information processing device comprising:

Images